打开codespace主页,选择blank template。
浏览器会自动在新的页面打开一个web版的vscode。
mkdir -p /workspaces/mindsearch
cd /workspaces/mindsearch
git clone https://github.com/InternLM/MindSearch.git
cd MindSearch && git checkout b832275 && cd ..
创建一个 conda 环境来安装相关依赖
# 创建环境
conda create -n mindsearch python=3.10 -y
# 激活环境
conda activate mindsearch
# 安装依赖
pip install -r /workspaces/mindsearch/MindSearch/requirements.txt
激活环境时报错:CondaError: Run ‘conda init‘ before ‘conda activate‘
解决:conda init --system --all
重新打开新的终端就可以解决。
获取硅基流动 API Key
因为要使用硅基流动的 API Key,所以接下来便是注册并获取 API Key 了。
首先,我们打开 硅基流动统一登录 来注册硅基流动的账号(如果注册过,则直接登录即可)。
在完成注册后,打开 硅基流动统一登录 来准备 API Key。首先创建新 API 密钥,然后点击密钥进行复制,以备后续使用。
启动 MindSearch
启动后端
由于硅基流动 API 的相关配置已经集成在了 MindSearch 中,所以我们可以直接执行下面的代码来启动 MindSearch 的后端。
#=复制的密钥
export SILICON_API_KEY=sk-bbkxwcvonmrnzmvujeuesrtdnveweabzvkohqjkyaganlsdn
conda activate mindsearch
cd /workspaces/mindsearch/MindSearch
python -m mindsearch.app --lang cn --model_format internlm_silicon --search_engine DuckDuckGoSearch
启动前端
在后端启动完成后,我们打开新终端运行如下命令来启动 MindSearch 的前端。
conda activate mindsearch
cd /workspaces/mindsearch/MindSearch
python frontend/mindsearch_gradio.py
部署到 HuggingFace Space
最后,我们来将 MindSearch 部署到 HuggingFace Space。
我们首先打开 https://huggingface.co/spaces ,并点击 Create new Space,如下图所示。
最后,我们先新建一个目录,准备提交到 HuggingFace Space 的全部文件。
# 创建新目录
mkdir -p /workspaces/mindsearch/mindsearch_deploy
# 准备复制文件
cd /workspaces/mindsearch
cp -r /workspaces/mindsearch/MindSearch/mindsearch /workspaces/mindsearch/mindsearch_deploy
cp /workspaces/mindsearch/MindSearch/requirements.txt /workspaces/mindsearch/mindsearch_deploy
# 创建 app.py 作为程序入口
touch /workspaces/mindsearch/mindsearch_deploy/app.py
import json
import os
import gradio as gr
import requests
from lagent.schema import AgentStatusCode
os.system("python -m mindsearch.app --lang cn --model_format internlm_silicon &")
PLANNER_HISTORY = []
SEARCHER_HISTORY = []
def rst_mem(history_planner: list, history_searcher: list):
'''
Reset the chatbot memory.
'''
history_planner = []
history_searcher = []
if PLANNER_HISTORY:
PLANNER_HISTORY.clear()
return history_planner, history_searcher
def format_response(gr_history, agent_return):
if agent_return['state'] in [
AgentStatusCode.STREAM_ING, AgentStatusCode.ANSWER_ING
]:
gr_history[-1][1] = agent_return['response']
elif agent_return['state'] == AgentStatusCode.PLUGIN_START:
thought = gr_history[-1][1].split('```')[0]
if agent_return['response'].startswith('```'):
gr_history[-1][1] = thought + '\n' + agent_return['response']
elif agent_return['state'] == AgentStatusCode.PLUGIN_END:
thought = gr_history[-1][1].split('```')[0]
if isinstance(agent_return['response'], dict):
gr_history[-1][
1] = thought + '\n' + f'```json\n{json.dumps(agent_return["response"], ensure_ascii=False, indent=4)}\n```' # noqa: E501
elif agent_return['state'] == AgentStatusCode.PLUGIN_RETURN:
assert agent_return['inner_steps'][-1]['role'] == 'environment'
item = agent_return['inner_steps'][-1]
gr_history.append([
None,
f"```json\n{json.dumps(item['content'], ensure_ascii=False, indent=4)}\n```"
])
gr_history.append([None, ''])
return
def predict(history_planner, history_searcher):
def streaming(raw_response):
for chunk in raw_response.iter_lines(chunk_size=8192,
decode_unicode=False,
delimiter=b'\n'):
if chunk:
decoded = chunk.decode('utf-8')
if decoded == '\r':
continue
if decoded[:6] == 'data: ':
decoded = decoded[6:]
elif decoded.startswith(': ping - '):
continue
response = json.loads(decoded)
yield (response['response'], response['current_node'])
global PLANNER_HISTORY
PLANNER_HISTORY.append(dict(role='user', content=history_planner[-1][0]))
new_search_turn = True
url = 'http://localhost:8002/solve'
headers = {'Content-Type': 'application/json'}
data = {'inputs': PLANNER_HISTORY}
raw_response = requests.post(url,
headers=headers,
data=json.dumps(data),
timeout=20,
stream=True)
for resp in streaming(raw_response):
agent_return, node_name = resp
if node_name:
if node_name in ['root', 'response']:
continue
agent_return = agent_return['nodes'][node_name]['detail']
if new_search_turn:
history_searcher.append([agent_return['content'], ''])
new_search_turn = False
format_response(history_searcher, agent_return)
if agent_return['state'] == AgentStatusCode.END:
new_search_turn = True
yield history_planner, history_searcher
else:
new_search_turn = True
format_response(history_planner, agent_return)
if agent_return['state'] == AgentStatusCode.END:
PLANNER_HISTORY = agent_return['inner_steps']
yield history_planner, history_searcher
return history_planner, history_searcher
with gr.Blocks() as demo:
gr.HTML("""<h1 align="center">MindSearch Gradio Demo</h1>""")
gr.HTML("""<p style="text-align: center; font-family: Arial, sans-serif;">MindSearch is an open-source AI Search Engine Framework with Perplexity.ai Pro performance. You can deploy your own Perplexity.ai-style search engine using either closed-source LLMs (GPT, Claude) or open-source LLMs (InternLM2.5-7b-chat).</p>""")
gr.HTML("""
<div style="text-align: center; font-size: 16px;">
<a href="https://github.com/InternLM/MindSearch" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">🔗 GitHub</a>
<a href="https://arxiv.org/abs/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📄 Arxiv</a>
<a href="https://huggingface.co/papers/2407.20183" style="margin-right: 15px; text-decoration: none; color: #4A90E2;">📚 Hugging Face Papers</a>
<a href="https://huggingface.co/spaces/internlm/MindSearch" style="text-decoration: none; color: #4A90E2;">🤗 Hugging Face Demo</a>
</div>
""")
with gr.Row():
with gr.Column(scale=10):
with gr.Row():
with gr.Column():
planner = gr.Chatbot(label='planner',
height=700,
show_label=True,
show_copy_button=True,
bubble_full_width=False,
render_markdown=True)
with gr.Column():
searcher = gr.Chatbot(label='searcher',
height=700,
show_label=True,
show_copy_button=True,
bubble_full_width=False,
render_markdown=True)
with gr.Row():
user_input = gr.Textbox(show_label=False,
placeholder='帮我搜索一下 InternLM 开源体系',
lines=5,
container=False)
with gr.Row():
with gr.Column(scale=2):
submitBtn = gr.Button('Submit')
with gr.Column(scale=1, min_width=20):
emptyBtn = gr.Button('Clear History')
def user(query, history):
return '', history + [[query, '']]
submitBtn.click(user, [user_input, planner], [user_input, planner],
queue=False).then(predict, [planner, searcher],
[planner, searcher])
emptyBtn.click(rst_mem, [planner, searcher], [planner, searcher],
queue=False)
demo.queue()
demo.launch(server_name='0.0.0.0',
server_port=7860,
inbrowser=True,
share=True)
在最后,将 /root/mindsearch/mindsearch_deploy 目录下的文件(使用 git)提交到 HuggingFace Space 即可完成部署了。将代码提交到huggingface space的流程如下:
首先创建一个有写权限的token。
然后从huggingface把空的代码仓库clone到codespace。
cd /workspaces/codespaces-blank
git clone https://huggingface.co/spaces/cyq121/mindsearchqq
# 把token挂到仓库上,让自己有写权限
git remote set-url space https://cyq121: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@huggingface.co/spaces/cyq121/mindsearchqq
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
git remote set-url space https://cyq121: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@huggingface.co/spaces/cyq121/mindsearchqq
报错:Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
解决:git init
报错:error: No such remote 'space'
解决:git remote -v #如果没有任何反应表示需要添加
git remote add space https://huggingface.co/spaces/cyq121/mindsearchqq
上面图片操作可略去,终端运行下面命令:
git remote set-url space https://cyq121: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@huggingface.co/spaces/cyq121/mindsearchqq
cd mindsearchqq
# 把刚才准备的文件都copy进来
cp /workspaces/mindsearch /workspaces/codespaces-blank/
1、配置用户信息
git config --global user.name [username]
git config --global user.email [email]
2、查询用户信息
git config --list
3、如果push遇到在输入密码是输错后,就会报这个错误fatal: Authentication failed for
解决办法:
git config --system --unset credential.helper
Linux中使用cp命令报cp:omitting directory错误
解决措施:cp -r 文件路径 目的路径
主要原因分析:要复制的文件下有子目录
https://blog.csdn.net/qq_33039859/article/details/139390796
git remote set-url origin https://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@huggingface.co/cyq121/my-new-model/